Quantum machine learning (QML) is increasingly proposed for predictive analytics in agriculture, yet two operational questions remain underexplored: platform reproducibility across open-source software-development kits (SDKs), and robustness under climate-distribution shift. This paper contributes a methodological reproducibility benchmark, not an agricultural result: a synthetic agronomic-suitability classification task on which a Quantum Support Vector Machine (QSVM) is trained identically across three SDKs (Qiskit, Cirq, PennyLane) with a fixed feature map. Across 40 independently generated train/test instances at the primary n = 60 operating point, all three SDKs produce identical predictions at every evaluated seed and regime; Qiskit and PennyLane agree at the double-precision floor and Cirq’s default kernel differs at approximately 1.8 × 10 − 7 , a gap that collapses under forced double precision and that an SDK-free, exact analytic evaluation of the same circuit reproduces to the same floor, directly showing that the present four-qubit circuit carries no computational quantum advantage. Under repeated climate-shift evaluation, the QSVM shows no statistically significant accuracy change under drought or extreme heat after Holm correction; under wet conditions, the QSVM and several non-linear classical baselines show a significant accuracy gain , with balanced accuracy and AUROC rising alongside raw accuracy, that moves opposite to a significant majority-class-baseline drop. Test-set class prevalence shifts sharply under wet, but prevalence change alone does not account for the gain, which is shared across several non-linear classical models and is therefore not specific to the QSVM. Both the cross-SDK parity finding and the general shape of the shift result replicate under two structurally different synthetic generators (correlated features; an alternative noisy decision rule), though the wet-regime effect weakens under correlated sampling. Three real-data anchors reproduce the same numerical pattern, with one isolated prediction-level exception. These results are limited to a synthetic benchmark and noise-free statevector simulators; they establish cross-SDK numerical reproducibility and controlled shift behaviour, not quantum advantage or field-level crop-yield validity.
Quantum machine learning (QML) is increasingly proposed for predictive analytics in agriculture, yet two operational questions remain underexplored: platform reproducibility across open-source software-development kits (SDKs), and robustness under climate-distribution shift. This paper contributes a methodological reproducibility benchmark, not an agricultural result: a synthetic agronomic-suitability classification task on which a Quantum Support Vector Machine (QSVM) is trained identically across three SDKs (Qiskit, Cirq, PennyLane) with a fixed feature map. Across 40 independently generated train/test instances at the primary n = 60 operating point, all three SDKs produce identical predictions at every evaluated seed and regime; Qiskit and PennyLane agree at the double-precision floor and Cirq’s default kernel differs at approximately 1.8 × 10 − 7 , a gap that collapses under forced double precision and that an SDK-free, exact analytic evaluation of the same circuit reproduces to the same floor, directly showing that the present four-qubit circuit carries no computational quantum advantage. Under repeated climate-shift evaluation, the QSVM shows no statistically significant accuracy change under drought or extreme heat after Holm correction; under wet conditions, the QSVM and several non-linear classical baselines show a significant accuracy gain , with balanced accuracy and AUROC rising alongside raw accuracy, that moves opposite to a significant majority-class-baseline drop. Test-set class prevalence shifts sharply under wet, but prevalence change alone does not account for the gain, which is shared across several non-linear classical models and is therefore not specific to the QSVM. Both the cross-SDK parity finding and the general shape of the shift result replicate under two structurally different synthetic generators (correlated features; an alternative noisy decision rule), though the wet-regime effect weakens under correlated sampling. Three real-data anchors reproduce the same numerical pattern, with one isolated prediction-level exception. These results are limited to a synthetic benchmark and noise-free statevector simulators; they establish cross-SDK numerical reproducibility and controlled shift behaviour, not quantum advantage or field-level crop-yield validity.
This paper presents a systematic empirical benchmarking of quantum machine learning (QML) applications within the under-explored domain of agricultural image classification. The authors implement and evaluate four hybrid quantum-classical architectures—including variational quantum classifiers (VQC), quanvolutional neural networks (QNN), and a ResNet-50 combined with a Quantum Support Vector Machine (QSVM)—against a purely classical EfficientNet baseline. The architectures are tested on three agricultural disease datasets: potato tuber disease, jujube insect pests, and paddy leaf rust. The experimental findings reveal that the ResNet-50+QSVM hybrid model achieves the optimal balance of classification accuracy and training stability, reaching a 93.4% mean accuracy. Crucially, the hybrid QSVM demonstrates extreme sample efficiency by requiring 41% fewer labeled training samples than the classical EfficientNet baseline to cross a 90% accuracy threshold, showing the capability of quantum feature maps in low-data regimes.
Reliable attribution of artificial intelligence (AI)-generated text to a specific large language model (LLM) matters increasingly as LLMs proliferate, yet where quantum machine learning actually stands on this task has, to our knowledge, never been measured systematically. We benchmark the quantum support vector machine (QSVM) for binary attribution between Gemma 3 and Qwen 2.5 on a 5800-sample corpus from paired prompts: 83 configurations sweeping qubit count, regularization, training-set size, feature-map family, and circuit depth under exact, noiseless classical statevector simulation. QSVM validation accuracy plateaus at approximately 88%, whereas a classical support vector machine with a radial basis function kernel reaches approximately 97.8% on the identical fourteen-dimensional inputs: the ceiling belongs to the quantum (fidelity) kernel, not to the input representation. We measure the mechanism: off-diagonal quantum kernel values shrink exponentially with qubit count, the signature of exponential kernel concentration. The same classical model recovers the stylometric attribution fingerprint, showing it belongs to the shared feature pipeline rather than to the quantum kernel. All large-scale headline results generalize to an independent 1000-text test set produced after every design decision was frozen. The study provides a cautionary, reproducible benchmark for quantum kernel natural language processing and outlines an open-set extension as future work.
Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous benchmarks against strong classical baselines remain scarce. We present a comprehensive empirical study of quantum kernel support vector machines (QSVMs) across nine binary classification datasets, four quantum feature maps, three classical kernels, and multiple noise models, totalling 970 experiments with strict nested cross-validation.
Our analysis spans four phases: (i) statistical significance testing, revealing that none of 29 pairwise quantum-classical comparisons reach significance at α=0.05; (ii) learning curve analysis over six training fractions, showing steeper quantum slopes on six of eight datasets that nonetheless fail to close the gap to the best classical baseline; (iii) hardware validation on IBM ibm_fez (Heron r2), demonstrating kernel fidelity r≥0.976 across six experiments; and (iv) seed sensitivity analysis confirming reproducibility (mean CV 1.4%).
A Kruskal-Wallis factorial analysis reveals that dataset choice dominates performance variance (ε2=0.73), while kernel type accounts for only 9%. Spectral analysis offers a mechanistic explanation: current quantum feature maps produce eigenspectra that are either too flat or too concentrated, missing the intermediate profile of the best classical kernel, the radial basis function (RBF). Quantum kernel training (QKT) via kernel-target alignment yields the single competitive result -- balanced accuracy 0.968 on breast cancer -- but with ~2,000x computational overhead.
Our findings provide actionable guidelines for quantum kernel research. The complete benchmark suite is publicly available to facilitate reproduction and extension.
Crop recommendation systems are very important in sustainable agriculture and yield optimization. Most of the traditional machine learning algorithms, such as SVM, do not work well on datasets for which there is a strong nonlinear relationship between the features such as soil parameters, climatic conditions and labels of crops. In this paper, we investigate the performance difference between classical SVM and Quantum Support Vector Machine (QSVM) when trained with highly complex, non-linear agriculture dataset. A synthetic non-linear dataset was constructed to mimic challenging real-world agriculture patterns, and is used to evaluate both the models fairly. Experimental results shows that classical SVM struggles to model deep feature dependencies, while QSVM significantly outperforms it by 10% increase in the accuracy due to the advantage of quantum feature encoding and high-dimensional Hilbert space mapping. This paper illustrates the potential benefits of quantum machine learning in different agricultural applications and indicates the advantages of quantum-enhanced models when dealing with challenging data sets.
Quantum Machine Learning (QML) has emerged as an active area of research, yet its practical readiness for real-world geospatial applications remains uncertain due to constraints related to data availability, preprocessing requirements, and current quantum hardware limitations. This study evaluates the feasibility and behaviour of quantum kernel-based learning models within a realistic GIS workflow, using land suitability analysis for reforestation in the Mumbai metropolitan region as a representative case study although demonstrated using the Mumbai metropolitan region as a case study, the proposed GIS-driven preprocessing pipeline and quantum kernel evaluation framework are transferable to other regions with comparable remote-sensing data availability and environmental indicators. A geospatial dataset is constructed from satellite-derived environmental variables, including Normalized Difference Vegetation Index (NDVI), annual rainfall, terrain slope, soil pH, and soil organic carbon, with suitability labels assigned using ecologically motivated rule-based thresholds that serve as heuristic ground truth. The dataset is processed through a standardized pipeline involving feature scaling, Principal Component Analysis (PCA), stratified train–test splitting, and Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. Quantum Support Vector Machines (QSVMs) employing Pauli and ZZ feature maps are implemented using Qiskit and evaluated under noiseless simulation conditions, with performance compared against a classical Support Vector Machine baseline using identical preprocessing and evaluation metrics. While classical models achieve superior computational efficiency and higher predictive performance, QSVMs exhibit non-trivial classification behaviour on small, structured datasets when appropriate preprocessing and feature-to-qubit alignment are applied. Rather than claiming quantum advantage, this work provides an empirical assessment of the current capabilities and limitations of QML in applied geospatial analysis, positioning quantum kernel methods as complementary tools for exploratory environmental modelling under present technological constraints.
Variational quantum classifiers (VQCs) are often compared with classical models under unequal data partitions, tuning budgets, or statistical treatment. We benchmark a 4-qubit VQC against logistic regression, an RBF-SVM, random forest, a quantum-kernel SVM (QSVM), and a majority-class control on Breast Cancer Wisconsin (n=569), Coimbra (n=116), and Golub leukemia (n=72), using five stratified folds across five seeds (25 paired blocks per dataset), identical training-fold-fitted preprocessing, and Nadeau–Bengio corrected paired tests with Holm correction. A first arm with a frozen configuration and the common [0, π] angle encoding left the VQC at 0.563, 0.515, and 0.576 accuracy (majority 0.617, 0.552, 0.652). In a second arm, in which every model was tuned by the same inner cross-validation and the encoding scale was a tuned hyperparameter, VQC accuracy rose to 0.864, 0.616, and 0.747. On Wisconsin the VQC stayed significantly below every matched classical model (differences 0.079–0.097, Holm p≤0.006) but above the majority class; on Golub it was significantly below only the SVM (Holm p=0.016); on Coimbra no comparison was significant. A QSVM with the same feature map exceeded the VQC numerically on every dataset, and three optimizers reached the same training loss in pilot diagnostics, pointing to the encoding and the variational head rather than the optimizer. The Wisconsin arms also differ in sample size (120 versus 569). Results apply to this low-qubit, PCA-compressed, exactly simulated setting and do not indicate a quantum advantage.